The structure and function of explanations.

By Tania Lombrozo. 2006

688 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Developmental and Educational Psychology, Philosophy

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Developmental and Educational Psychology

In Philosophy

Citations in the corpus

ALICE: Active Learning with Contrastive Natural Language Explanations (2020, background): “Psychologists and philosophers have long posited natural language explanations as central, organizing elements to human learning and reasoning (Chin-Parker and Cantelon, 2017; Lombrozo, 2006; Smith, 2003).”
Can language models learn from explanations in context? (2022, background): “, 1992)— explanations highlight task principles that allow us to generalize broadly (Lombrozo and Carey, 2006; Lombrozo, 2006).”
Towards A Rigorous Science of Interpretable Machine Learning (2017, background): “A formal deﬁnition of explanation remains elusive; in the ﬁeld of psychology, Lombrozo [2006] states “explanations are... the currency in which we exchanged beliefs” and notes that questions such as what constitutes an explanation, what makes some explanations better than others, how explanations…”
Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI (2019, background): “Lombrozo (2006); Lombrozo et al. (2008); Lombrozo (2016) Describe research and psychological theory on explanation with a focus on cognitive development.”
Explanation in Artificial Intelligence: Insights from the Social Sciences (2017, background): “Explanation is both a process and a product, as noted by Lombrozo [104].”
Handling Model Uncertainty and Multiplicity in Explanations via Model Reconciliation (2018, methodology): “Explanations of this form have been inspired by works like (Lombrozo 2006; 2012; Miller 2017) which identify properties of explanations in terms of selectivity, contrastiveness and mental modeling of the explainee, and our recent work (Chakraborti et al.”
Textual Explanations for Self-Driving Vehicles (2018, background): “Visual and Textual Explanations: The importance of explanations for an end-user has been studied from the psychological perspective [17,18], showing that humans use explanations as a guide for learning and understanding by building inferences and seeking propositions or judgments that enrich their p”
RISE: Randomized Input Sampling for Explanation of Black-box Models (2018, background): “There is extensive evidence for the importance of explanation towards understanding and building trust in cognitive psychology [15], philosophy [16] and machine learning [6, 14, 21] research.”
How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanation (2018, background): “Human explanations typically appeal to causal structure [Lombrozo, 2006] and counterfactuals [Keil, 2006].”
Grounding Visual Explanations (2018, background): “The importance of explanations for humans has been studied in the field of psychology [14,15], showing that humans use explanations as a guide for learning and understanding by building inferences and seeking propositions or judgments that enrich their prior knowledge.”
Finding new facts; thinking new thoughts. (2012, neutral): “…an appeal to plausible causal, mechanistic relations; Bonawitz & Lombrozo, in press; Hempel & Oppenheim, 1948; Keil & Wilson, 2000; Keleman, 1999; Kitcher, 1989; Legare, Gelman, & Wellman, 2010; Lombrozo, 2006, 2007, 2012; Lombrozo & Carey, 2006; Salmon, 1984; Strevens, 2004; Woodward, 2009).”
Explanations in the wild. (2021, neutral): “…(Bechlivanidis et al., 2017; Gopnik, 2000; Hopkins et al., 2016; Horne et al., 2019; Keil, 2006; Kelemen & Ros-set, 2009; Liquin & Lombrozo, 2022; Lombrozo, 2006; Zemla et al., 2017, among others), our explanations-in-the-wild approach highlights several desiderata of a cognitive theory of…”
Causal-explanatory pluralism: How intentions, functions, and mechanisms influence causal ascriptions. (2010, background): “…mechanisms, which I refer to as ‘‘mechanistic,” and forwards-looking explanations that cite functions or goals, which I refer to as ‘‘teleological,” has proved fruitful in characterizing different ways of understanding properties and events (e.g. Keil, 2006; Lombrozo, 2006; Lombrozo & Carey, 2006).”
Explanation and Abductive Inference (2012, background): “Generating and evaluating explanations may be mechanisms by which prior beliefs are brought to bear on a given task (Lombrozo, 2006), especially in knowledge-rich domains.”
Explainable Artificial Intelligence: a Systematic Review (2020, background): “As highlighted in [112], two properties of the structure of an explanation can have a significant effect on learning, namely the capacity to “accommodate novel information in the context of prior beliefs and do so in a way that fosters generalization”.”
Tell me why! Explanations support learning relational and causal structure (2021, background): “Explanations help humans to understand causal structure (Lombrozo, 2006; Lombrozo & Carey, 2006).”